FocalAPI Docs
Guides

Audio Creation

Use transcription, translation, and text-to-speech APIs

FocalAPI provides three audio entry points for creative workflows: transcription, translation, and speech synthesis. Model IDs, voices, file limits, and supported formats are defined by GET /v1/models and the model catalog in the console.

Transcription

curl https://api.focalapi.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $FOCALAPI_KEY" \
  -F "model=<transcription-model>" \
  -F "file=@interview.mp3"

Text to speech

curl https://api.focalapi.com/v1/audio/speech \
  -H "Authorization: Bearer $FOCALAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<speech-model>",
    "voice": "<available-voice>",
    "input": "Welcome to the FocalAPI creative workflow."
  }' \
  --output narration.mp3

Audio outputs, available voices, and billing units are model-specific. Validate a short sample before producing long or batch audio.

On this page